Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a valid modality for nodal lung cancer staging. The sonographic features of EBUS helps determine suspicious lymph nodes (LNs). To facilitate this use of this method, machine-learning-based computer-aided diagnosis (CAD) of medical imaging has been introduced in clinical practice. This study investigated the feasibility of CAD for the prediction of nodal metastasis in lung cancer using endobronchial ultrasound images. Image data of patients who underwent EBUS-TBNA were collected from a video clip. Xception was used as a convolutional neural network to predict the nodal metastasis of lung cancer. The prediction accuracy of nodal metastasis through deep learning (DL) was evaluated using both the five-fold cross-validation and hold-out methods. Eighty percent of the collected images were used in five-fold cross-validation, and all the images were used for the hold-out method. Ninety-one patients (166 LNs) were enrolled in this study. A total of 5255 and 6444 extracted images from the video clip were analyzed using the five-fold cross-validation and hold-out methods, respectively. The prediction of LN metastasis by CAD using EBUS images showed high diagnostic accuracy with high specificity. CAD during EBUS-TBNA may help improve the diagnostic efficiency and reduce invasiveness of the procedure.
Background/Objectives: Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a well-established, minimally invasive method for sampling mediastinal and hilar lymph nodes. It has high sensitivity and specificity for diagnosing lymph node involvement. However, achieving a definitive cytopathological diagnosis can be challenging owing to the limited presence of atypical tumor cells. The scanning single-molecule counting (SSMC) method enables rapid measurement of target molecule expression. This study assessed the correlation between miR-200c expression measured by SSMC and lymph node metastasis confirmed by cytopathology. Methods: Following EBUS-TBNA in patients with lung cancer or suspected lung cancer, we flushed 22-gauge biopsy needles with 1 mL saline and extracted microRNA (miRNA) from the lavage fluid. The quality of SSMC results for miR-200c was evaluated and compared with that of quantitative real-time polymerase chain reaction (RT-qPCR). Results: Linear regression analysis of miR-200c between SSMC and RT-qPCR showed a statistically significant positive correlation (R2 = 0.81, p < 0.0001), demonstrating the feasibility of SSMC for evaluating miRNA in lymph nodes. Based on these findings, we enrolled and analyzed 100 lymph nodes from 86 patients. High miR-200c expression detected lymph node metastasis with high sensitivity (85.7%) and specificity (83.3%) and an AUC of 0.88. No discordance was observed between the standard SSMC and rapid methods. Conclusions: The expression of miR-200c, as measured by SSMC, may serve as a biomarker for molecular nodal staging. The rapid SSMC method provides results within 30 min, significantly faster than conventional RT-qPCR, and may complement rapid on-site cytological evaluation.
1 December 2025 in Video-Assisted Thoracic Surgery
Thoracic endometriosis-related pneumothorax (TERP) is a pneumothorax caused by endometrial tissue in the thoracic cavity, including the diaphragm and the visceral and parietal pleura. Video-assisted thoracic surgery (VATS) is considered an effective treatment option for TERP, but the high recurrence rate after surgery remains an issue. To reduce the high recurrence rate, we have introduced the following surgery technique as a basic treatment strategy for TERP: partial diaphragm resection plus reconstruction; partial lung resection; resection and cauterization of dorsal pleural endometriotic lesions; and pleural covering. This time, we introduced uniportal VATS for TERP surgery. In this article, we describe in detail uniportal VATS partial diaphragm resection plus reconstruction; partial lung resection; resection and cauterization of dorsal pleural lesions; and pleural covering procedures with videos. Additionally, the results of several cases in which this surgical technique has been performed are reported. From November 2023 to March 2025, uniportal VATS surgery for TERP was performed on six cases. The operative time, blood loss, postoperative drainage period, and hospital stay period were 162.5±9.7 min, 68.3±132.1 g, 3.1±0.4 days, and 5.6±0.5 days, respectively. No recurrence of pneumothorax after surgery was observed. Uniportal VATS for TERP considering, the extent of thoracic endometriosis lesions, might be safe and effective in preventing postoperative pneumothorax recurrence.